Big data-based time-space confusion exposure degree assessment system and method

Abstract

The invention relates to a big data-based time-space confusion exposure degree assessment system and method. The system comprises a time-space data mining block, a multi-source heterogeneous data fusion module, a final variable selection module, a time-space generalized additive model building module, a re-sampling model module, a variation function time-space modeling module and a concentration estimation module; massive time-space data is mined; a relationship between multiple influence factors and pollutant concentration is established by adopting an accumulative nonlinear method; and through residual variation function fitting, spatial autocorrelation is considered, so that the prediction precision and effect are greatly improved.

Description

technical field [0001] The invention relates to a time-space confusion exposure evaluation system and method based on massive big data, belonging to the technical field of environmental health. Background technique [0002] The current monitoring data of environmental pollutants is sparse, and early data is lacking. However, the spatio-temporal resolution of the existing calculation model prediction is extremely limited, making it difficult to achieve refined pollutant estimation. PM 2.5 For example, in recent years, the problem of air pollution has become increasingly prominent, and the impact of air pollutants on human health has aroused great public concern. PM is the most harmful air pollutant to human health 2.5 . At present, the research on air pollution at home and abroad is also based on PM 2.5 is the focus, but it is affected by various environmental factors and human factors, and is limited by the time scale and spatial scale of monitoring data, making the PM ...

AI Technical Summary

Problems solved by technology

At present, the research on air pollution at home and abroad is also based on PM 2.5 is the focus, but it is affected by various environmental factors and human factors, and is limited by the time scale and spatial scale of monitoring data, making the PM 2.5 There are certain uncertainties in the prediction of concentration, and it is difficult to make efficient and accurate prediction

However, due to the fact that domestic related research has just started, the monitoring data is sparse for the vast areas of China, which in turn affects the accuracy of public health effect assessment. Therefore, an efficient, accurate and low-error prediction method is urgently needed for public health research. to protect the safety of the public

[0003] In short, the existing environmental exposure such as PM 2.5 The main disadvantage of the estimation method is the limited auxiliary data and the lack of big data support; the model algorithm used lacks the consideration of spatial correlation, which also limits the further application of these methods

Images